AI Paper Atlas

Research map / Detection and segmentation / 3D detection and driving

2D-Driven 3D Object Detection in RGB-D Images

Jean Lahoud, Bernard Ghanem

ICCV 2017 · Detection and segmentation › 3D detection and driving · approach: Unified LiDAR 3D detection · 180 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add MLP box regression for object center and extent (ablation)2D-driven 3D detector · SUN RGB-D (10 classes)mAP (%): 21.26 -> 45.12Improved
estimate per-box orientation instead of a fixed room orientation (ablation)2D-driven 3D detector · SUN RGB-D (10 classes)mAP (%): 30.24 -> 45.12Improved
add context-based factor-graph refinement (ablation)2D-driven 3D detector · SUN RGB-D (10 classes)mAP (%): 42.79 -> 45.12Improved
add context-based refinement (ablation)2D-driven 3D detector · SUN RGB-D (10 classes)runtime per image: 2.7s -> 4.15sHurt
use the proposed method instead of DSS2D-driven 3D detector · SUN RGB-D (10 classes)mAP (%): 42.1 -> 45.1Improved
use the proposed method instead of COG2D-driven 3D detector · SUN RGB-D (10 classes)mAP (%): 47.63 -> 45.12Mixed

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy